4 people 35d44b4557 [XPU]Support CUDAGraph on XPU Platform (#34482) ...

Signed-off-by: Xinyu Chen <xinyu1.chen@intel.com>
Co-authored-by: chzhang <chaojun.zhang@intel.com>
Co-authored-by: zhenwei-intel <zhenwei.liu@intel.com>
Co-authored-by: Kunshang Ji <kunshang.ji@intel.com>

2026-02-24 22:22:52 -08:00

..

gpu

[Model Runner V2] Remove propose_draft method (#35070)

2026-02-22 18:27:12 -08:00

__init__.py

[V1] Implement vLLM V1 [1/N] (#9289)

2024-10-22 01:24:07 -07:00

block_table.py

[V1][Hybrid] Mamba Prefix Caching with align mode (#30877)

2026-01-23 09:56:48 -08:00

cp_utils.py

[V1][Hybrid] Mamba Prefix Caching with align mode (#30877)

2026-01-23 09:56:48 -08:00

cpu_model_runner.py

[Feature] OTEL tracing during loading (#31162)

2026-02-05 16:59:28 -08:00

cpu_worker.py

[Core] Profiler improvements and lazy initialization (#33198)

2026-02-12 16:16:38 -08:00

dp_utils.py

[feature] extend DBO to XBO (#30120)

2025-12-16 00:04:01 -05:00

ec_connector_model_runner_mixin.py

[Misc] Introduce ec_both role EC (encoder cache) connector (#34182)

2026-02-10 18:55:35 +00:00

gpu_input_batch.py

[V1][Hybrid] Mamba Prefix Caching with align mode (#30877)

2026-01-23 09:56:48 -08:00

gpu_model_runner.py

[Platform] Add current_platform.num_compute_units interface (#35042)

2026-02-24 22:22:49 -08:00

gpu_ubatch_wrapper.py

[Platform] Add current_platform.num_compute_units interface (#35042)

2026-02-24 22:22:49 -08:00

gpu_worker.py

[Feature] Pipeline Parallel Async send/recv, 2.9% E2E throughput improvement (#33368)

2026-02-13 16:38:16 +08:00

kv_connector_model_runner_mixin.py

[Spec Decode] Defer clearing KV connector metadata for EAGLE3 speculative decode + prefill / decode disagg setup (#34529)

2026-02-22 08:08:32 -08:00

lora_model_runner_mixin.py

Reduce the kernel overhead when num of active loras is smaller than max loras. Multiple cuda graphs are captured for each num of active-loras. (#32005)

2026-02-02 12:30:06 -05:00

mamba_utils.py

[Linear Attention] fix bug for linear attention + prefix caching + reset_prefix_cache (#35157)

2026-02-24 22:00:19 -08:00

tpu_input_batch.py

[Cleanup] Remove unused ModelRunner V1 InputBatch.num_tokens field (#30218)

2025-12-18 09:17:00 -08:00

ubatch_utils.py

[6/N][Attention] Move utils to more appropriate locations (#32215)

2026-01-13 05:38:52 -08:00

ubatching.py

[Misc] Replace Optional[X] with X | None syntax (#33332)

2026-01-30 01:56:59 -08:00

utils.py

[Refactor] Move profiling methods to MM budget (#33559)

2026-02-02 23:27:00 +08:00

worker_base.py

[Feature] OTEL tracing during loading (#31162)

2026-02-05 16:59:28 -08:00

workspace.py

[Misc] Replace Optional[X] with X | None syntax (#33332)

2026-01-30 01:56:59 -08:00

xpu_model_runner.py

[XPU]Support CUDAGraph on XPU Platform (#34482)

2026-02-24 22:22:52 -08:00

xpu_worker.py

[XPU][1/N] Deprecate ipex and switch to vllm-xpu-kernels for xpu platform (#33379)

2026-02-02 22:46:10 -08:00